Browsing by Author "Yuadi, Imam"

Now showing 1 - 11 of 11

A visible wavelet watermarking technique based on exploiting the contrast sensitivity function and noise reduction of human vision system
(2014-09-01)
Tsai, Min-Jen
;
Liu, Jung
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
With the widespread use of the Internet and the rapid development of digital technologies, copyright protection of multimedia content has become an important issue. Among the available technologies, digital watermarking techniques are regarded as a solution to the property right protection for multimedia resources. To evaluate the performance of a visible watermarking technique, robustness and perceptual translucence are two essential criteria for the watermark applications. In order to get the best trade-off between the embedding energy of a watermark and perceptual translucence, this study presents a technique named ICOCOA (innovated content and contrast aware) by exploiting the contrast sensitivity function (CSF) and noise reduction of human vision system in the wavelet domain. Another novel idea of this work is to propose the innovated CSF masking (I-CSF) curve which provides better weight perception where a game-theoretic architecture can be leveraged to determine the best I-CSF masking for the watermarked image. The experimental results demonstrate that the proposed approach not only provides a good translucent quality of the watermark but also achieves the robustness against the common image processing operations.
Decision-theoretic model to identify printed sources
(2018-10-01)
Tsai, Min-Jen
;
Yuadi, Imam
;
Tao, Yu-Han
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
When trying to identify a printed forged document, examining digital evidence can prove to be a challenge. Over the past several years, digital forensics for printed document source identification has begun to be increasingly important which can be related to the investigation and prosecution of many types of crimes. Unlike invasive forensic approach which requires a fraction of the printed document as the specimen for verification, noninvasive forensic technique uses the optical mechanism to explore the relationship between the scanned images and the source printer. To explore the relationship between source printers and images obtained by the scanner, the proposed decision-theoretical approach utilizes image processing techniques and data exploration methods to calculate many important statistical features, including: Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, the Wiener filter, the Gabor filter, Haralick, and SFTA features. Consequently, the proposed aggregation method intensively applies the extracted features and decision-fusion model of feature selections for classification. In addition, the impact of different paper texture or paper color for printed sources identification is also investigated. In the meantime, the up-to-date techniques based on deep learning system is developed by Convolutional Neural Networks (CNNs) which can learn the features automatically to solve the complex image classification problem. Both systems have been compared and the experimental results indicate that the proposed system achieve the overall best accuracy prediction for image and text input and is superior to the existing approaches. In brief, the proposed decision-theoretical model can be very efficiently implemented for real world digital forensic applications.
Deep learning for printed document source identification
(2019-02-01)
Tsai, Min-Jen
;
Tao, Yu-Han
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Due to the rapid development of the information technology and wide use of the Internet, Information is easily to be obtained in the form of digital format. Digital content can be freely printed into documents since the convenience and accessibility of the printers. On the other hand, printed documents can be illegally manipulated by some criminal issues such as: forged documents, counterfeit currency, copyright infringement, and so on. Therefore, how to develop an efficient and appropriate safety testing tool to identify the source of printed documents is an important task in the meantime. Currently, the forensic system using the statistical methods and support vector machine technology has been able to identify the source printer for the text and the image documents. Such an approach belongs to the category of shallow machine learning with human interaction during the stages of feature extraction, feature selection and data pre-processing. In this paper, a deep learning system to solve the complex image classification problem is developed by Convolutional Neural Networks (CNNs) of deep learning which can learn the features automatically. Systematic experiments have been performed for both systems. For microscopic documents, feature based SVM system outperforms the deep learning system with limited gap. For scanned documents, both system can achieve equally well with high accuracy. Both systems should be constantly evaluated and compared for the best interest in universal utilization.
Digital Forensics for Printed Character Source Identification
(2016)
Tsai, Min-Jen
;
Hsu, Chien-Lun
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
Even digital content is widely used nowadays, printed documents are still ubiquitously accepted and circulated. Therefore, identifying the printed character source is essential for criminal investigations to authenticate the digital copies of the printed documents. This study carefully examines the important statistical features from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, and Gabor filter to identify the printer source for Chinese characters by using support vector machine (SVM) and decision fusion of feature selection. Even the subject of printed Chinese character source identification has been investigated, the proposed technique further expands the feature space which achieves superior experimental results and outperforms the techniques described in the literatures. Therefore, the methodology proposed in this study can accomplish high classification accuracy rate which show promising applications for real world digital forensics.
Digital forensics of microscopic images for printed source identification
(2018-04-01)
Tsai, Min-Jen
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
When trying to identify a printed forged document, examining digital evidence can prove to be a challenge. In this study, microscopic images are used for printed source identification due to their high magnification properties resulting in detailed texture and structure information. Prior research implemented a scanner as a digitizing technique to resolve very fine printed identification, but this technique provided limited information on the resolution and magnification of the sample. In contrast, the performance of microscopy techniques can retrieve the shape and surface texture of a printed document with differing micro structures among printer sources. To explore the relationship between source printers and images obtained by the microscope, the proposed approach utilizes image processing techniques and data exploration methods to calculate many important statistical features, including: Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, the Wiener filter, the Gabor filter, Haralick, and SFTA features. Among the different set of features, the LBP approach achieves the highest identification rate and is significantly superior to other methods. As a result, the proposed technique using microscopic images achieves a high classification accuracy rate, which shows promising applications for real world digital forensics research.
Digital Forensics of Printed Source Identification for Chinese Characters
(2014-01-01)
Tsai, Min-Jen
;
Liu, Jung
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
Recently, digital forensics, which involves the collection and analysis of the origin digital device, has become an important issue. Digital content can play a crucial role in identifying the source device, such as serve as evidence in court. To achieve this goal, we use different texture feature extraction methods such as gray-level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT), to analyze the Chinese printed source in order to find the impact of different output devices. Furthermore, we also explore the optimum feature subset by using feature selection techniques and using support vector machine (SVM) to identify the source model of the documents. The average experimental results attain a 98.64 % identification rate which is significantly superior to the existing known method by 1.27 %. The superior testing performance demonstrates that the proposed identification method is very useful for source laser printer identification.
Digital forensics of printed source identification for Chinese characters
(2014-12-01)
Tsai, Min-Jen
;
Yin, Jin-Shen
;
Yuadi, Imam
;
Liu, Jung
;
資訊管理與財務金融系註：原資管所+財金所
Recently, digital forensics, which involves the collection and analysis of the origin digital device, has become an important issue. Digital content can play a crucial role in identifying the source device, such as serve as evidence in court. To achieve this goal, we use different texture feature extraction methods such as graylevel co-occurrence matrix (GLCM) and discrete wavelet transform (DWT), to analyze the Chinese printed source in order to find the impact of different output devices. Furthermore, we also explore the optimum feature subset by using feature selection techniques and use support vector machine (SVM) to identify the source model of the documents. The average experimental results attain a 98.64 % identification rate which is significantly superior to the existing known method of GLCM by 1.27 %. The superior testing performance demonstrates that the proposed identification method is very useful for source laser printer identification.
Japanese Character based Printed Source Identification
(2015)
Tsai, Min-Jen
;
Hsu, Chien-Lun
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
Due to the advances of digital technology, digital contents are widely accepted all over the world. Since the criminal counterfeits and copyright infringement is still under study for the new digital media, there is an increasing need called digital forensics, which involves the collection and analysis of the original digital device, has become an important issue. This study offers a universal approach to extract the important statistical features from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filter, Wiener filter and Gabor filter to identify the printer source for Japanese characters. The average experimental results achieves high identification rate at 94.23% which is significantly superior to the existing known method of using GLCM at 77.31%. The result is also better than the technique for Chinese character identification method at 88.77%. This superior testing performance demonstrates that the proposed identification technique is very effective for Japanese character based source laser printer identification.
Printed Source Identification by Microscopic Images
(2016)
Tsai, Min-Jen
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
The research of printed source identification is generally processed by scanned images which are limited by the scanner resolution. The accuracy of source identification is also bound by this limitation. In this study, microscopic images are used for printed source identification based on its high magnification capability for detailed texture and structure information. To explore the relationship between source printers and images obtained by the microscope, the proposed approach utilizes image processing techniques and data exploration methods to calculate many important features, i.e., Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filter and Haralick filter. Among different set of features, LBP approach achieves the highest identification rate which is significantly superior to other methods. Consequently, the proposed technique using microscopic images achieves high classification accuracy rate which show promising applications for real world digital forensics research.
Source Identification for Printed Documents
(2017-01-01)
Tsai, Min-Jen
;
Yuadi, Imam
;
Yin, Jin-Sheng
;
Tao, Yu-Han
;
資訊管理與財務金融系註：原資管所+財金所
Technological advances in digitization with a variety of image manipulation techniques enable the creation of printed documents illegally. Correspondingly, many researchers conduct studies in determining whether the document printed counterfeit or original. This study examines the several statistical feature sets from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filter, Haralick and fractal filters to identify text and image document by using support vector machine (SVM) and decision fusion of feature selection. The average experimental results achieves that the image document is higher identification rate than text document. In summary, the proposed method outperforms the previous researches and it is a promising technique that can be implemented in real forensics for printed documents.
Tree group based Wavelet Watermarking using Energy Modulation and Consistency Check (WW-EMCC) for digital images
(2015-12-01)
Tsai, Min-Jen
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Wavelet tree based watermarking algorithms are generally using the energy difference among grouped wavelet coefficients for invisible watermark embedding and extraction. According to cryptanalysis of wavelet tree quantization (WTQ) scheme, the robustness of watermarking is weak if the wavelet tree group coefficients are only unilaterally modulated. Therefore, bilaterally modulated techniques like modified wavelet tree quantization (MWTQ) and wavelet tree group modulation (WTGM) improve the security since the attackers can not decipher how tree coefficients are modulated. However, MWTQ needs the wavelet tree group information as the extra information which results the method is not purely blind for watermark extraction. For that matter, a novel wavelet tree group based watermarking using energy modulation and consistency check (WW-EMCC) is proposed in this study which not only resists the cryptanalysis attacks but also provides the dual function of choices for blind (WW-EMCCB) and non-blind (WW-EMCCN) watermark embedding. The essence of WW-EMCC design is to embed the watermark in the tree group coefficients as well as the relationship between the tree groups. Such approach extends the bilateral modulation into higher dimension of modulation and increase the robustness of security. In addition, WW-EMCC can even be modified as a captioning watermarking with lossless image quality which integrates watermarking and cryptography for copyright protection. This study has performed intensive comparison for the proposed scheme with WTQ, MWTQ and WTGM under various geometric and nongeometric attacks. The experimental results demonstrate that the proposed technique yields better performance with higher degree of robustness.